RSIAgent：先广后深的课程式训练让智能体在陌生应用中表现更好
一篇关于智能体训练的论文：让智能体先广泛练相关任务再啃难题，4 个任务上从 56.50% 提到 74.54%，附独立校验设计，做 agent 的可以看看。
论文 RSIAgent 提出一种无需重新采集数据训练智能体的方法：由课程智能体自造练习任务，actor 用代码解题，另有独立 verifier 校验结果。练习策略是先在相关任务上广泛探索，再深入目标任务的困难案例。在 4 个任务上，先广后深的智能体平均得分 74.54%，直接攻难题的对照组为 56.50%，差距约 18 个百分点。
Agents that explored widely before tackling hard cases averaged 74.54% on 4 tasks, versus 56.50% when they went straight to the hard cases, so start wide.
AI agents often fumble in unfamiliar apps. The usual fix is collecting new data and retraining, which is expensive.
In RSIAgent, a curriculum agent invents practice tasks, an actor solves them with code, and a separate verifier checks each result. Practice starts broad across related tasks, then goes deep on the real task and its hard cases.
Overall the paper says, Before putting an agent to work in a new app, let it practice broad, then deep, with a separate verifier deciding what's saved.
